Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3631 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.2205. Min Range: -5.2205
Max Act: 5.2205. Min Act: -0.1700
Data Index: 330044 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2205. Min Range: -5.2205
Max Act: 5.1580. Min Act: -0.1700
Data Index: 6117304 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2205. Min Range: -5.2205
Max Act: 5.1893. Min Act: -0.1700
Data Index: 3949721 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2205. Min Range: -5.2205
Max Act: 5.1580. Min Act: -0.1698
Data Index: 7145633 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2205. Min Range: -5.2205
Max Act: 5.1580. Min Act: -0.1700
Data Index: 6093655 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2205. Min Range: -5.2205
Max Act: 5.1268. Min Act: -0.1699
Data Index: 6939654 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2205. Min Range: -5.2205
Max Act: 5.0955. Min Act: -0.1700
Data Index: 3166139 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2205. Min Range: -5.2205
Max Act: 5.0955. Min Act: -0.1700
Data Index: 3284191 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2205. Min Range: -5.2205
Max Act: 5.0955. Min Act: -0.1700
Data Index: 830516 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2205. Min Range: -5.2205
Max Act: 5.0955. Min Act: -0.1700
Data Index: 5126567 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2205. Min Range: -5.2205
Max Act: 5.0330. Min Act: -0.1700
Data Index: 4969118 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2205. Min Range: -5.2205
Max Act: 5.0643. Min Act: -0.1700
Data Index: 5489121 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2205. Min Range: -5.2205
Max Act: 5.0330. Min Act: -0.1700
Data Index: 7904248 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2205. Min Range: -5.2205
Max Act: 5.0330. Min Act: -0.1700
Data Index: 8790202 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2205. Min Range: -5.2205
Max Act: 5.0330. Min Act: -0.1700
Data Index: 3544985 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2205. Min Range: -5.2205
Max Act: 5.0018. Min Act: -0.1700
Data Index: 1222904 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2205. Min Range: -5.2205
Max Act: 5.0018. Min Act: -0.1700
Data Index: 4054271 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2205. Min Range: -5.2205
Max Act: 5.0330. Min Act: -0.1699
Data Index: 4969117 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2205. Min Range: -5.2205
Max Act: 5.0018. Min Act: -0.1700
Data Index: 7328970 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2205. Min Range: -5.2205
Max Act: 5.0018. Min Act: -0.1700
Data Index: 1941440 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #19